Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
527464 | Image and Vision Computing | 2008 | 9 Pages |
Abstract
The frequent problem in low-level vision arises from the goal to eliminate noise and uninteresting details from an image, without blurring semantically important structures such as edges. Partial differential equations (PDEs) have recently dominated image processing research, as a very good tool for noise elimination, image enhancement and edge detection. In this paper, we present a biased PDE filter based on a coupling between shock filter and curvature diffusion. This model removes noise and sharpens edges efficiently. It preserves well the location of the shocks by synchronising both effects of smoothing and deblurring. Empirical results on different kinds of images confirm these advantages.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Computer Vision and Pattern Recognition
Authors
Salim Bettahar, Amine Boudghene Stambouli,